M

model-orchestration

Manager/worker orchestration for Claude Code: keep your smartest model as the manager and delegate implementation and token-hungry work to isolated headless workers backed by any Anthropic-compatible API (z.ai GLM, Kimi, DeepSeek, LiteLLM proxies)

divyamrastogi/model-orchestration · v0.8.1 · Development & Workflow

divyamrastogiOwner verifiedcaution

Trust Score

67

Security

59

Surfaces

1

What is model-orchestration?

model-orchestration is a published development & workflow plugin for AI coding agents in the claude-code ecosystem, developed by divyamrastogi and distributed through the HOL AI plugin registry. Manager/worker orchestration for Claude Code: keep your smartest model as the manager and delegate implementation and token-hungry work to isolated headless workers backed by any Anthropic-compatible API (z.ai GLM, Kimi, DeepSeek, LiteLLM proxies)

Canonical slug
divyamrastogi/model-orchestration
Version
v0.8.1 · updated Oct 7, 2026

Trust & Reputation

HOL Trust Score
67

Factor Analysis

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
64pts
Maintenance
55pts
MCP Posture
100pts
Plugin Security
59pts
Provenance
70pts
Publisher Quality
75pts

Registry Snapshot

Publisher verification
No
Marketplace source
Unknown
Scanner
Broker fallback
Safety label
caution
Digest verified
Yes
1 bundled skill — copy or download SKILL.mdOpen skills

Trust & reputation

Trust & Reputation

HOL Trust Score
67

Factor Analysis

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
64pts
Maintenance
55pts
MCP Posture
100pts
Plugin Security
59pts
Provenance
70pts
Publisher Quality
75pts

Provenance

Plugin root
.
Source repo
https://github.com/divyamrastogi/model-orchestration
Source commit
7698c40194fd…
Publisher verified
No
Owner verified
@divyamrastogi

Continuous scanner CI detected

No action is required. This plugin receives the full trust score.

Verified badge not detected

Add the HOL verified badge to the repository README to score +2% trust. Plugin owners can open that pull request from Guard Plugins.

Security Posture

caution
Safety label
59
Security score
0
High findings
Provider
registry-broker-fallback
Grade
F · caution
Version
Unknown
cisco-skill-scanner: unknown

Findings

mediumpublishabilitypublishability.link.missing.websiteURL

websiteURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.privacyPolicyURL

privacyPolicyURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.termsOfServiceURL

termsOfServiceURL should be present for marketplace readiness.

lowoperational-securitysupply-chain.lockfile-missing

Repository snapshot does not include a lockfile.

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

model-orchestration — Frequently asked questions

What is model-orchestration?
model-orchestration is an AI plugin in the HOL registry. Manager/worker orchestration for Claude Code: keep your smartest model as the manager and delegate implementation and token-hungry work to isolated headless workers backed by any Anthropic-compatible API (z.ai GLM, Kimi, DeepSeek, LiteLLM proxies)
How do I install model-orchestration?
Install model-orchestration in your harness: Claude Code — /plugin marketplace add divyamrastogi/model-orchestration; Any agent — npx skills add divyamrastogi/model-orchestration. Full step-by-step guidance is on the HOL plugin page.
How do I install model-orchestration in Claude Code?
To install model-orchestration in Claude Code, start with /plugin marketplace add divyamrastogi/model-orchestration. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
Is model-orchestration free?
Pricing for model-orchestration is published on its HOL plugin page when the maker schedules a launch.
Who publishes model-orchestration?
model-orchestration is published by divyamrastogi and listed on HOL.
Is model-orchestration available now?
model-orchestration availability is listed on its HOL plugin page.

Install Guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs
  1. 1

    Add the marketplace

    Run this inside a Claude Code session.

    claude code
  2. 2

    Install the plugin

    Use the plugin name and the marketplace name shown by the previous command.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell

Plugin Manifest

{
  "name": "model-orchestration",
  "version": "0.8.1",
  "description": "Manager/worker orchestration for Claude Code: keep your smartest model as the manager and delegate implementation and token-hungry work to isolated headless workers backed by any Anthropic-compatible API (z.ai GLM, Kimi, DeepSeek, LiteLLM proxies, ...).",
  "author": {
    "name": "Divyam Rastogi"
  },
  "homepage": "https://github.com/divyamrastogi/model-orchestration",
  "repository": "https://github.com/divyamrastogi/model-orchestration",
  "license": "MIT",
  "keywords": [
    "orchestration",
    "delegation",
    "multi-model",
    "glm",
    "workers",
    "cost-optimization"
  ],
  "interface": {
    "displayName": "model-orchestration",
    "developerName": "divyamrastogi"
  },
  "skills": "./",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 5
}

Marketplace Source

Repo URL
https://github.com/divyamrastogi/model-orchestration
Marketplace path
Unknown
Source path
.
Install policy
Unspecified

Skills

1 SKILL.md file ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • orchestrating-model-workers

    skills/orchestrating-model-workers/SKILL.md

    Use when the user wants to delegate work to cheaper or alternate models inside Claude Code — e.g. z.ai GLM, Kimi, DeepSeek, MiniMax, OpenRouter/LiteLLM proxies, or any Anthropic-compatible API — or asks about multi-model orchestration, manager/worker setups, headless worker instances, routing token-hungry work to a flat-rate coding plan, running a second provider alongside their Anthropic subscription, or when a spawned claude -p worker fails with "401 Invalid bearer token" or "Not logged in - Please run /login", or before dispatching any subtask while model-orchestration delegation defaults are active.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File Inventory

.claude-plugin/plugin.json

file

671 bytes

ae4b821bddef6f25…

.codex-plugin/plugin.json

plugin-manifest

749 bytes

77a3d996dc700415…

agents/worker-dispatch.md

file

2,376 bytes

b6b4609a2f431f93…

commands/delegate.md

file

1,325 bytes

6e153c455ccad914…

commands/savings.md

file

587 bytes

36186e78f9d440bf…

commands/setup-worker.md

file

2,083 bytes

78fe4715823a01c1…

hooks/hooks.json

file

661 bytes

7323187f1b0823c3…

hooks/post-dispatch.sh

file

400 bytes

36083d6385da8627…

hooks/session-start.sh

file

6,926 bytes

5417d24bf23f1914…

README.md

file

7,388 bytes

1d9bb8a6a811523a…

SECURITY.md

file

1,470 bytes

fc214e09a8ecdf0e…

skills/orchestrating-model-workers/SKILL.md

skill

10,826 bytes

76dd0784470ab86b…

skills/orchestrating-model-workers/templates/delegation-rules.md

skill

1,097 bytes

435f7e0342b5c8c8…